AI RESEARCH
Learning Dynamic Structural Specialization for Underwater Salient Object Detection
arXiv CS.CV
•
ArXi:2605.15535v1 Announce Type: new Underwater salient object detection (USOD) has attracted increasing attention for underwater visual scene understanding and vision-guided robotic applications. However, existing USOD methods still struggle with underwater image degradations, which often lead to inaccurate object localization, fragmented salient regions, and coarse boundary prediction. To address these challenges, this paper proposes DSS-USOD, a novel RGB-based USOD method built upon dynamic structural specialization.